| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004162222626882755, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00041622226268827554, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00041622226268827554, | |
| "eval_loss": NaN, | |
| "eval_runtime": 327.3095, | |
| "eval_samples_per_second": 12.364, | |
| "eval_steps_per_second": 6.184, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008324445253765511, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012486667880648266, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012486667880648266, | |
| "eval_loss": NaN, | |
| "eval_runtime": 171.2123, | |
| "eval_samples_per_second": 23.637, | |
| "eval_steps_per_second": 11.822, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016648890507531022, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0020811113134413775, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002497333576129653, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002497333576129653, | |
| "eval_loss": NaN, | |
| "eval_runtime": 171.1188, | |
| "eval_samples_per_second": 23.65, | |
| "eval_steps_per_second": 11.828, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0029135558388179287, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0033297781015062043, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00374600036419448, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00374600036419448, | |
| "eval_loss": NaN, | |
| "eval_runtime": 171.141, | |
| "eval_samples_per_second": 23.647, | |
| "eval_steps_per_second": 11.827, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004162222626882755, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.378799358836736e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |